ASR_SRT API Documentation

🌐 Language Switch

中文版 | English

Interface Information

POST /openapi/autosubrt/v1/asr/srt

This is the speech recognition service

The base URL of this interface is https://autosubrt.jcaigc.cn, which is a different service (and a different path prefix) from CapCut Mate (https://capcut-mate.jcaigc.cn).

Full URL = https://autosubrt.jcaigc.cn + /openapi/autosubrt/v1/asr/srt

Function Description

Speech recognition: transcribe audio into an SRT subtitle file and return the file body itself to the caller (Content-Disposition: attachment). Nothing is written to disk server-side and no download link is returned.

For the copy or timeline data use ASR; to align your own text against the audio use Align Text To Audio.

Request Parameters

{
  "audio_url": "https://example.com/audio.mp3",
  "apiKey": "123e4567-e89b-12d3-a456-426614174000"
}

Parameter Description

Parameter	Type	Required	Default	Description
audio_url	string	✅	-	Audio file URL, must be downloadable by the server and a valid http/https URL
apiKey	string	Required when billing is on	-	A valid UUID; get one at https://jcaigc.cn

Parameter Details

audio_url

• Type: string
• Description: The server downloads this URL before transcribing, so it must be a direct, publicly reachable link (not a page that requires login)
• Format: Any common audio or video file: wav, mp3, m4a, aac, flac, ogg; video files such as mp4 and mov also work (the audio track is extracted server-side)
• Limit: 100MB per file (server-side FILE_SIZE_LIMIT, 104857600 bytes by default)

apiKey

• Type: string
• Description: Must be a valid UUID; required while billing is enabled (it is by default), and the account balance must be greater than 1

Response Format

Success Response (200)

On success the response is not JSON — the body is the SRT file content:

HTTP/1.1 200 OK
Content-Type: application/x-subrip; charset=utf-8
Content-Disposition: attachment; filename="subtitle.srt"

1
00:00:02,810 --> 00:00:03,330
多谢

2
00:00:04,889 --> 00:00:06,009
请入席吧

Response Header Description

Header	Value	Description
Content-Type	application/x-subrip; charset=utf-8	Subtitle file; application/json on failure
Content-Disposition	attachment; filename="subtitle.srt"	Fixed file name subtitle.srt

Error Response

On failure a JSON error body is returned (still with HTTP 200). Tell the two apart by Content-Type:

{
  "code": 2003,
  "message": "Download file failed"
}

Content-Type	Meaning
application/x-subrip; charset=utf-8	An SRT subtitle file
application/json	An error; read code for the reason

Usage Examples

cURL Examples

curl -X POST https://autosubrt.jcaigc.cn/openapi/autosubrt/v1/asr/srt \
  -H "Content-Type: application/json" \
  -d '{
    "audio_url": "https://example.com/audio.mp3",
    "apiKey": "123e4567-e89b-12d3-a456-426614174000"
  }' \
  -o subtitle.srt

Python Example

import requests

resp = requests.post(
    "https://autosubrt.jcaigc.cn/openapi/autosubrt/v1/asr/srt",
    json={
        "audio_url": "https://example.com/audio.mp3",
        "apiKey": "123e4567-e89b-12d3-a456-426614174000",
    },
    timeout=600,
)

# A failure returns a JSON error body, not a subtitle file
if resp.headers["Content-Type"].startswith("application/json"):
    raise RuntimeError(resp.json()["message"])

with open("subtitle.srt", "wb") as f:
    f.write(resp.content)

Billing

This interface is charged by audio duration and shares the same points system as CapCut Mate.

Item	Description
Price	0.00022 points / second
Basis	Actual audio duration in seconds, as reported by the recognition engine
When charged	Only after a successful recognition; failures are not charged
Balance gate	The account must hold more than 1 point before the call, otherwise it is rejected (2035)

Audio duration	Cost (points)
10 seconds	0.002200
60 seconds	0.013200
1 hour	0.792000

apiKey must be a valid UUID and can be obtained at https://jcaigc.cn.

Error Code Description

Error Code	Error Message	Description	Solution
1001	Parameter validation failed	audio_url missing or not a valid http/https URL, or apiKey is not a valid UUID	Check the request parameters
2001	Failed to recognize audio	Audio could not be decoded, model not loaded, or audio_url returned 401/403/404	Try a playable file or a reachable direct link
2002	File size exceeds the limit	Audio is larger than 100MB	Compress or trim it and retry
2003	Download file failed	Network or server error during download, still failing after retries	Make sure it is a public direct download link
2005	Download file timeout	Overall download timed out	Use a faster source or a smaller file
2035	Insufficient account balance	The account needs more than 1 point to keep using the service	Recharge and retry
2036	Invalid apiKey	apiKey missing while billing is enabled	Get an apiKey at https://jcaigc.cn
9997	Server is busy	Concurrency limit reached; the request was not queued	Retry later
9998	Internal server error	Unexpected internal error	Contact technical support
9999	Unknown error	Points service unavailable, etc.	Retry later

Notes

1. The body is the file itself, not {code, message, data}: the old data.srt_url download-link form is gone, so callers must branch on Content-Type.
2. The file is UTF-8 with \n line endings, indices start at 1, and timestamps use HH:MM:SS,mmm.
3. Cues are split on silence: a gap of more than 250 milliseconds between two characters starts a new cue; if the whole audio cannot be split it becomes a single cue.
4. SRT text does not pass through the punctuation model: it comes straight from the recognition result and usually carries no punctuation (unlike text from ASR).
5. When no speech is recognized at all, one empty cue from 0s to 30s is returned; treat an empty cue text as "no speech".
6. Nothing is stored server-side: the temp audio is deleted when the request finishes, so there are no static files to clean up.
7. Repeated calls are charged repeatedly; do not blindly retry after a timeout.

Workflow

1. Validate apiKey and account balance (while billing is enabled)
2. Download the audio/video behind audio_url into a server-side temp directory
3. Run speech recognition to obtain per-character timelines
4. Split the character sequence into cues on silence gaps
5. Charge by audio duration after a successful recognition
6. Return the SRT file body as UTF-8 text, then delete the temp file

Related Interfaces

• ASR
• ASR Text
• Align Text To Audio

---

📚 Project Resources
GitHub: https://github.com/Hommy-master/autosubrt